July 2014 Newsletter

This month, in our Newsletter we present two recent articles that caught our attention and decided to share with you:

  1. The first one speaks to the application of Predictive models to increase Customer Retention and maximize Revenue
  2. The second one is focused on Embedding Analytics in your operations

Analytics Boost Customer Retention for Ohio Mutual 


Customer Retention

Ohio Mutual Insurance Group leverages SAS Business Analytics to significantly increase renewal premium income while simultaneously boosting policyholder retention.

By Anne Rawland Gabriel@insurancetech, 
September 23rd, 2013 


To capitalize on its investments in current policy-holders, Ohio Mutual Insurance Group recently began seeking a way to quantify the acceptable size of premium increases. "We had been using $50 as our maximum premium increase," explains Dave Grove, VP of product management for the Bucyrus, Ohio, insurer. "But, this was mostly intuitive rather than based on hard data."


After some internal discussions earlier this year, Ohio Mutual decided it already owned the appropriate technology tool for the job. "We'd implemented SAS (Cary, N.C.) Enterprise Business Intelligence Server in 2009 for month-end processing and reporting," says Grove.


"At that time we also brought onboard several long-term SAS users, including our head actuary," he adds. "That individual has over 25 years of SAS experience."  For its new need, Ohio Mutual sought to leverage the SAS Business Analytics component of the SAS solution. "Given our experience with SAS thus far, we were confident it could tackle the topic," Grove asserts.


By late spring Ohio Mutual began building and testing an analytics model using homeowner's policies in Ohio to kick off the initiative. The model segmented customers by various weighted characteristics such as the length of time a customer has been a policyholder, how many policies a customer held and what types of policies are held.  Almost immediately, Ohio Mutual discovered that a price-centric focus was too narrow. "When we started, we looked solely at the dollar amount," Grove recalls. "If we only wanted to retain 85% of our current customers, the dollar amount of premium increases could be much higher." 
Fish Jumping
But, 85% retention for Ohio Mutual was actually a step backwards. "Our historical renewal rate is 87%," says Grove. "And the profitability of our renewal business, versus obtaining new customers, is as much as 15 or 20%."  This led Ohio Mutual to add retention to the analytics model. "During the first week we decided to retool the model," confirms Grove. "We considered the dollar amount and retention rate." 

Within three weeks Ohio Mutual had actionable information regarding Ohio policyholders. "For some segments we could increase premiums by as much as $150 to $175 annually," Grove reports. "For others, it was $45 to $50."  What's more, retention rates would actually increase. "We're aiming to improve retention between one-half and one-and-a-half percent," says Grove. "If we could push retention to 88% or 89%, while adding to the size of the rate increase in certain segments, it would have a significant profitability impact."


Today Ohio Mutual is preparing to roll out the rate increases as homeowners policies renew throughout 2014. However, the company is so confident with the data it's already started to model other lines. "We're already working on personal automobile," Grove acknowledges. "We'll continue down the path for other personal lines."  As results flow in during 2014, Ohio Mutual intends to continue adjusting the tool and applying it to other business lines and regions. "We may need to tweak the model to achieve our goals throughout our personal lines before moving on to commercial lines," says Grove.  "However," he continues, "if the initial model meets or exceeds the high end of our retention goals for homeowner's policies in Ohio, we'll start working on our commercial lines immediately."


Regardless, Ohio Mutual also envisions utilizing the tool to enable other profitability goals. "The model will absolutely assist us with growing our New England book of business, which we acquired in 2011," Grove says.  "We implemented new auto and home products in those five states within the past year," he adds. "We'll apply the methodology to those renewals as well." 


In fact, Grove is so keen on the prospects for applying analytics that he suggests it could lead to other market opportunities. "Expansion is always on our horizon," he says. 

Embedding advanced analytics in your business process

To get the most value and greatest insight from your analytics, embed your analytics into your business processes.

By Fern Halper, July 1, 2014 

As advanced analytics begins to hit the mainstream, so, too, does the move to embed analytics into the business process. When you embed analytics, you actually insert it into the operational systems that are part of a process. For example, a statistician might build a predictive model that predicts what customers will purchase. If the model is not embedded into a business process, then it provides insight, and it may be acted upon manually, but it may not provide significant value.   

If that model is embedded into systems that feed the call center, however, the output of the model can be used by a call center agent as part of a business process -- say, to upsell or cross sell a customer who is on the line. Based on the behavior of other customers with a specific profile, a message to the agent might appear on the agent's screen when the customer calls in. The agent doesn't need to know how the model works, just how to work the offer.


Another example is analytics embedded into a system at the point of sale. An algorithm (for recommendations, for example) might be running behind the scenes. Based on what the customer is buying, the recommendation system might provide some coupons if the customer is in a physical location. If the customer is online, it might suggest some other items a customer might buy. 


TDWI Research indicates that companies are starting to embrace operationalizing and even embedding advanced analytics into their systems and processes.


In our 2014 Predictive Analytics Best Practices Survey, for instance, at least a third of those respondents who were using predictive modeling were operationalizing it as part of a business process. Some of this may be part of a manual process today, but more companies will embed the analytics into systems as part of a workflow in the next few years. 


There are numerous reasons why this is important:

  • It makes advanced analytics more consumable. When analytics are embedded into business systems, the end result is that analytics become more consumable, which means that more people can make use of sophisticated analytics output. I've written about this as a kind of multiplier effect in previous articles and blog postings. One person might build the model, but the output of the model is available to far more people. That means that insightful and valuable output from predictive models can be utilized across the organization. 
  • It makes analytics actionable. Analysis without action is not that useful. When you embed analytics into a process, it means that the output can be actionable. When used together with business rules and operationalizing it, action can be taken. This might be done semi-automatically or automatically.   That can be a big advantage for companies. For instance, a fraud application can utilize embedded analytics to detect probable fraud based on the characteristics of the transaction and automatically route the instance to a customer for verification or a special investigation unit. A preventive maintenance application can monitor assets for issues based on past patterns or rules and trigger alerts that can improve performance and save money. 
  • It makes analytics more valuable. As analytics become part of a workflow, it can provide top- and bottom-line impact. The examples above support this. Automating analytics can reduce costs associated with manually trying to deal with the output. The analytics can be utilized by more parties to drive benefits. Operationalizing and embedding analytics makes organizations more productive. Many organizations doing this feel that it is a competitive differentiator. 
  • When analytics are embedded into business systems and processes, the analytics can become more prescriptive. Prescriptive analytics is a form of advanced analytics that utilizes predictive analytics and suggests options based on predictive output. Some people consider this the next evolution of predictive analytics (where predictive was the next stage in sophistication from descriptive analytics). Predictive analytics helps determine what is going to happen; prescriptive analytics can help you take action. A recommender system we described is one example of a prescriptive analytics system. Examples in varying shapes and level of complexity can be found across all industries. 

To learn more, please visit us at www.tdtanalytics.com 
or contact
+1 (416) 900-0360 Ext 10  

Connect with us on these social networks: